app.py

import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""
    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content
        response += token
        yield response


with gr.Blocks() as demo:
    system_message = gr.Textbox(
        label="System Message",
        value="You are a helpful assistant.",
        lines=2,
    )
    chat_history = gr.State([])

    with gr.Row():
        with gr.Column(scale=0.8):
            chatbot = gr.Chatbot()
        with gr.Column(scale=0.2):
            max_tokens = gr.Slider(
                minimum=1, maximum=512, step=1, value=128, label="Max Tokens"
            )
            temperature = gr.Slider(
                minimum=0, maximum=1, step=0.01, value=0.7, label="Temperature"
            )
            top_p = gr.Slider(
                minimum=0, maximum=1, step=0.01, value=1, label="Top-p"
            )

    user_input = gr.Textbox(show_label=False, placeholder="Type your message here...")

    def user_interaction(message, history, system_message, max_tokens, temperature, top_p):
        bot_message = next(respond(message, history, system_message, max_tokens, temperature, top_p))
        history.append((message, bot_message))
        return history, history

    user_input.submit(
        user_interaction,
        inputs=[user_input, chat_history, system_message, max_tokens, temperature, top_p],
        outputs=[chatbot, chat_history],
    )

if __name__ == "__main__":
    demo.launch()